COMPAT: Add Pathlib, py.path support for read_hdf

Closes #11773

Author: John Evans <[email protected]>

Closes #12930 from quintusdias/issue11773 and squashes the following commits:

dcee282 [John Evans] COMPAT: Add Pathlib, py.path support for read_hdf, to_hdf

Author: quintusdias

doc/source/whatsnew/v0.18.2.txt

@@ -32,6 +32,7 @@ Other enhancements
 - The ``.tz_localize()`` method of ``DatetimeIndex`` and ``Timestamp`` has gained the ``errors`` keyword, so you can potentially coerce nonexistent timestamps to ``NaT``. The default behaviour remains to raising a ``NonExistentTimeError`` (:issue:`13057`)
 
 - ``Index`` now supports ``.str.extractall()`` which returns ``DataFrame``, see :ref:`Extract all matches in each subject (extractall) <text.extractall>` (:issue:`10008`, :issue:`13156`)
+- ``.to_hdf/read_hdf()`` now accept path objects (e.g. ``pathlib.Path``, ``py.path.local``) for the file path (:issue:`11773`)
 
   .. ipython:: python
 

pandas/io/pytables.py

@@ -13,10 +13,12 @@
 import os
 
 import numpy as np
+
 import pandas as pd
 from pandas import (Series, DataFrame, Panel, Panel4D, Index,
                     MultiIndex, Int64Index)
 from pandas.core import config
+from pandas.io.common import _stringify_path
 from pandas.sparse.api import SparseSeries, SparseDataFrame, SparsePanel
 from pandas.sparse.array import BlockIndex, IntIndex
 from pandas.tseries.api import PeriodIndex, DatetimeIndex
@@ -254,6 +256,7 @@ def to_hdf(path_or_buf, key, value, mode=None, complevel=None, complib=None,
     else:
         f = lambda store: store.put(key, value, **kwargs)
 
+    path_or_buf = _stringify_path(path_or_buf)
     if isinstance(path_or_buf, string_types):
         with HDFStore(path_or_buf, mode=mode, complevel=complevel,
                       complib=complib) as store:
@@ -270,7 +273,11 @@ def read_hdf(path_or_buf, key=None, **kwargs):
 
         Parameters
         ----------
-        path_or_buf : path (string), or buffer to read from
+        path_or_buf : path (string), buffer, or path object (pathlib.Path or
+            py._path.local.LocalPath) to read from
+
+            .. versionadded:: 0.18.2 support for pathlib, py.path.
+
         key : group identifier in the store. Can be omitted a HDF file contains
             a single pandas object.
         where : list of Term (or convertable) objects, optional
@@ -293,6 +300,7 @@ def read_hdf(path_or_buf, key=None, **kwargs):
     if 'where' in kwargs:
         kwargs['where'] = _ensure_term(kwargs['where'], scope_level=1)
 
+    path_or_buf = _stringify_path(path_or_buf)
     if isinstance(path_or_buf, string_types):
 
         try:
@@ -316,6 +324,7 @@ def read_hdf(path_or_buf, key=None, **kwargs):
 
         store = path_or_buf
         auto_close = False
+
     else:
         raise NotImplementedError('Support for generic buffers has not been '
                                   'implemented.')

pandas/io/tests/test_pytables.py

@@ -4836,6 +4836,42 @@ def test_read_nokey(self):
             df.to_hdf(path, 'df2', mode='a')
             self.assertRaises(ValueError, read_hdf, path)
 
+    def test_read_from_pathlib_path(self):
+
+        # GH11773
+        tm._skip_if_no_pathlib()
+
+        from pathlib import Path
+
+        expected = DataFrame(np.random.rand(4, 5),
+                             index=list('abcd'),
+                             columns=list('ABCDE'))
+        with ensure_clean_path(self.path) as filename:
+            path_obj = Path(filename)
+
+            expected.to_hdf(path_obj, 'df', mode='a')
+            actual = read_hdf(path_obj, 'df')
+
+        tm.assert_frame_equal(expected, actual)
+
+    def test_read_from_py_localpath(self):
+
+        # GH11773
+        tm._skip_if_no_localpath()
+
+        from py.path import local as LocalPath
+
+        expected = DataFrame(np.random.rand(4, 5),
+                             index=list('abcd'),
+                             columns=list('ABCDE'))
+        with ensure_clean_path(self.path) as filename:
+            path_obj = LocalPath(filename)
+
+            expected.to_hdf(path_obj, 'df', mode='a')
+            actual = read_hdf(path_obj, 'df')
+
+        tm.assert_frame_equal(expected, actual)
+
 
 class TestHDFComplexValues(Base):
     # GH10447